DocumentCode
316815
Title
Statistical recognition methods application for isolated word recognition
Author
Bovbe, Evgeny I. ; Kheidoro, Igor E.
Author_Institution
Dept. of Radiophys., Byelorussian State Univ., Minsk, Byelorussia
Volume
2
fYear
1997
fDate
2-4 Jul 1997
Firstpage
821
Abstract
This paper is devoted to the problem of effective isolated word recognition using a priory acoustical information about the vocabulary. It is proposed to implement the HMM method to estimate the acoustic phoneme probabilities and use them as inputs for the acoustic-phonetic hidden Markov model specially designed for the given phonetic context. The experiment shows that such approach can be successfully used for isolated word recognition
Keywords
acoustic signal processing; hidden Markov models; probability; speech recognition; statistical analysis; HMM method; acoustic phoneme probabilities; acoustic-phonetic hidden Markov model; experiment; isolated word recognition; statistical recognition methods; vocabulary; Hidden Markov models; Image recognition; Probability; Signal processing; Speech processing; Speech recognition; Statistical analysis; Statistics; Tin; Vocabulary;
fLanguage
English
Publisher
ieee
Conference_Titel
Digital Signal Processing Proceedings, 1997. DSP 97., 1997 13th International Conference on
Conference_Location
Santorini
Print_ISBN
0-7803-4137-6
Type
conf
DOI
10.1109/ICDSP.1997.628479
Filename
628479
Link To Document